A valid request URL is required to generate request examples
{ "id": "<string>", "object": "chat.completion", "created": 123, "model": "<string>", "choices": [ { "index": 123, "message": { "role": "system", "content": "<string>", "name": "<string>", "tool_calls": [ { "id": "<string>", "type": "function", "function": { "name": "<string>", "arguments": "<string>" } } ], "tool_call_id": "<string>" }, "finish_reason": "stop", "logprobs": { "content": [ { "token": "<string>", "logprob": 123, "bytes": [ 123 ], "top_logprobs": [ { "token": "<string>", "logprob": 123, "bytes": [ 123 ] } ] } ] } } ], "usage": { "prompt_tokens": 123, "completion_tokens": 123, "total_tokens": 123, "prompt_tokens_details": { "cached_tokens": 123 }, "completion_tokens_details": { "reasoning_tokens": 123, "accepted_prediction_tokens": 123, "rejected_prediction_tokens": 123 }, "cache_creation_input_tokens": 123, "cache_read_input_tokens": 123 }, "system_fingerprint": "<string>" }
Implements the OpenAI Realtime Protocol over WebSockets for ultra-low latency audio and text. Supports stateful session recovery using the session_id parameter.
session_id
API key passed as a Bearer token.
(Optional) Previous session ID to recover conversation state.
The model identifier to use for the session.
Switching Protocols to WebSocket.
Was this page helpful?